{"title":"A hardware efficient VLSI architecture for FFT processor in OFDM systems","authors":"Jianming Wu, Ke Liu, Bo Shen, Hao Min","doi":"10.1109/ICASIC.2005.1611255","DOIUrl":null,"url":null,"abstract":"This paper presents a hardware efficient FFT implementation architecture using a novel data access scheme for OFDM applications. By conversion of digit-reversed to bit-reversed order addressing, continuous flow FFT processing can be achieved using 2 N-word memories by alternation between natural order and bit-reversed order addressing. An in-place multi-bank memory is adopted to accommodate high-speed applications such as wireless multimedia communications. Also the bank index generation is performed using bit-wise XOR operations instead of conventional modulo-r additions. The scheme supports scalable length FFT computation and achieves conflict-free memory access","PeriodicalId":431034,"journal":{"name":"2005 6th International Conference on ASIC","volume":"79 1","pages":"0"},"PeriodicalIF":0.0000,"publicationDate":"2005-10-24","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"10","resultStr":null,"platform":"Semanticscholar","paperid":null,"PeriodicalName":"2005 6th International Conference on ASIC","FirstCategoryId":"1085","ListUrlMain":"https://doi.org/10.1109/ICASIC.2005.1611255","RegionNum":0,"RegionCategory":null,"ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"","JCRName":"","Score":null,"Total":0}
引用次数: 10
Abstract
This paper presents a hardware efficient FFT implementation architecture using a novel data access scheme for OFDM applications. By conversion of digit-reversed to bit-reversed order addressing, continuous flow FFT processing can be achieved using 2 N-word memories by alternation between natural order and bit-reversed order addressing. An in-place multi-bank memory is adopted to accommodate high-speed applications such as wireless multimedia communications. Also the bank index generation is performed using bit-wise XOR operations instead of conventional modulo-r additions. The scheme supports scalable length FFT computation and achieves conflict-free memory access